Share:
One of the functions Twitter provides its users is the “Who to Follow” list. When you click on an account, a small box pops up with similar accounts as potential, new accounts to follow. While this might appear beneficial on the surface—it’s deeply problematic if a real user accidentally lands on a fake account.
When looking at a fake account, Twitter’s algorithms recommend “similar” fake accounts. As a matter of fact, Twitter’s algorithms are so good at identifying similar fake accounts that they’ll recommend fake accounts from the same “botnet.”
It’s been long-known that Twitter’s “recommended accounts to follow” algorithm is a tip-off for fake accounts within the same bot groups. This is easily seen with the basic model bots and their fake male distributors.
Using the easy-to-identify female model bots, here are some clear examples of how Twitter’s algorithms push additional fake accounts to real users.
Below are fake male accounts that help distribute the female model bots (in their followers). Again, Twitter’s algorithms identify accounts from the same fake account group and recommend them as “Who to Follow.”
A Closer Look at the Patterns
The fact that the recommended accounts are from the same botnet becomes obvious when looking at each of their accounts. Notice that they all share:
1 > Similar tweet numbers
2 > Similar Following and Follower numbers
3 > Almost all of the followers are female model bots
Let’s take a closer look at the “Who to Follow” on the account below.
The first account on the list is “Glenn Hicks.”
The second “Who to Follow” account is “Mike Vokmar.”
And the last “Who to Follow” account is “hammer0938.”
The Uptake on Twitter’s Algorithms
What Twitter’s “Who to Follow” lists tell us:
Twitter’s algorithms know that these accounts are connected.
This begs the question: Why doesn’t Twitter get rid of the obviously fake, interconnected accounts? They can’t claim that their algorithms don’t detect them. And while Twitter executives continuously claim that they are cleaning up their platform—this article in of itself is a case-study in Twitter’s actual, minuscule efforts.
Written by Unhackthevote
Read More about Fake Twitter Accounts:
Locked Bot and Troll Accounts Fly Under the Radar
A Flood of Russian Twitter bots with English names
Follow us:
